23c4e63a68
An independent model reviewed the MCP and OAuth surfaces. All five findings were verified against the code before changing anything; none were false positives. audit.md is kept as the record of what was reviewed. F1 (High) - refresh reuse detection forgot the token family. Only the current hash and one predecessor lived on the grant, and each rotation overwrote the predecessor. A thief who rotated a stolen token twice made the victim's original unrecognisable: replaying it returned "unknown token" instead of revoking the family, and the thief kept working. Refresh tokens are now rows in OAuthRefreshToken, one per generation, retained for the life of the family and consumed by a guarded update on usedAt - which also means two concurrent uses of the same token can no longer both succeed. This corrects a claim I made when the OAuth server shipped: reuse detection covered one generation, not the family. F2 (Medium) - issueAccessToken wrote scopes back onto the grant, so redeeming a stale authorization code redefined standing consent. Token issuance is not consent; the consent endpoint is now the only writer. Codes are additionally bound to a grant id and epoch, with a coversScopes check behind that. F3 (Medium) - revocation was reversible. Reconnecting a disconnected app cleared revokedAt and left credentials that had raced the revoke usable again. Every approval now starts a clean epoch: the counter advances and prior access tokens, refresh tokens and unconsumed codes are destroyed. Token writes are conditional on the epoch they validated, so a revoke that wins a race aborts them. Refresh also now requires offline_access to still be granted. F4 (Medium) - loopback redirect matching compared only scheme, host and path, silently accepting a differing query, fragment or userinfo. RFC 9700 2.1 wants exact matching apart from the RFC 8252 port exception; that is what it does now. F5 (Low) - get_collection_stats returned bar and recipe counts under drinks:read. Gated on the caller actually holding bar:read. Verified with regression tests for each: the two-rotation attack now revokes the family, concurrent refresh yields exactly one winner, a pre-narrowing code is refused, disconnect-reconnect leaves old credentials dead, and Claude Code's ephemeral-port callback still works while query/userinfo/fragment variants are rejected. Existing protections re-checked - code replay, PKCE mismatch, deny, confidential-client rejection, and the MCP tools themselves. Note for deploy: OAuthAuthCode gains a required grantId, so existing rows must be cleared first. They are 60-second ephemeral codes. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01W1Ee4Mc1X1SX8HgYa52zu7
This is a Next.js project bootstrapped with create-next-app.
Getting Started
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
Open http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
AI Gateway (Switchboard)
All AI features — menu scanning, label identification, drink search, the bartender
and the recommendation engine — go through Switchboard,
an OpenAI-compatible gateway that routes each request to the best available model.
The app never pins a model id; it always sends switchboard/auto and lets the gateway
choose, then logs which model answered and what it cost.
Setup:
- Set
SWITCHBOARD_BASE_URLin your env file (defaults tohttp://192.168.2.11:8787/v1). - Mint an API key in the Switchboard UI under Settings → API keys.
- Add that key in the app under Settings → AI Gateway.
Per-feature routing (cost/quality levers, token budgets, timeouts) lives in
src/lib/ai/routing.ts. Note that a Switchboard key carries its own routing defaults,
so the app sets category and prefer_free explicitly on every request rather than
inheriting whatever the key was minted for.
Migrating from the old Claude/OpenAI integration
Earlier versions stored a per-user Anthropic or OpenAI key. Those rows are ignored at runtime and the Settings page offers to remove them, so no migration is required. To clear them in bulk instead:
DELETE FROM "UserApiKey" WHERE provider IN ('claude','openai');
DELETE FROM "SearchCache" WHERE provider IN ('claude','openai');
UPDATE "UserPreference" SET "defaultProvider" = NULL;
Learn More
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
Deploy on Vercel
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more details.